Yolo11-FED: An Improved Object Detection Algorithm for Driving Scenarios
Abstract
used to replace the original SPPF module. This module uses convolutional layers with different dilation rates to extract features of different
scales. Low inflation rate captures local details, while high inflation rate captures global context. And use shared convolutional layers to reduce the number of training parameters. Next, we will use the Efficient Unified Context Block (EUCB) in the neck to extract richer features
through upsampling and depthwise separable convolution. Channel shuffling promotes communication between different channels and enhances feature expression ability. Finally, a dynamic head (DyHead) is used in the detection head, which utilizes dynamic convolution to
automatically adjust channel weights based on input features, optimize feature representation, and enhance inspection accuracy and efficiency.
The comparison and ablation experiments on the Cityscapes dataset show that our model achieved an average accuracy of 47.2 (mAP@0.5)
Exceeding the baseline YOLO11n by 3.9%. The experimental results confirm that yolo11-FED significantly improves the detection accuracy
of urban objects (such as pedestrians, vehicles, etc.) in driving scenarios, promoting the development of autonomous driving.
Keywords
Full Text:
PDFReferences
[1] X. Chen, J. Guan, Z. Wang, H. Zhang and G. Wang, "Marine Targets Detection for Scanning Radar Images Based on RadarYOLONet," 2021 CIE International Conference on Radar (Radar), Haikou, Hainan, China, 2021, pp. 1256-1260, doi: 10.1109/
Radar53847.2021.10028264.
[2] N. Yao, W. Chen, J. Qin and G. Shan, "Research on the Image Model of Substation UAV Inspection Based on the Improved YOLO Algorithm," 2024 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), Shenzhen, China,
2024, pp. 61-64, doi: 10.1109/ICICML63543.2024.10957790.
[3] Z. Yue, C. -W. Sham, C. Y. Lo, W. Cheung and C. Y. Yiu, "Sea View Extension for Semantic Segmentation in Cityscapes,"
2023 9th International Conference on Applied System Innovation (ICASI), Chiba, Japan, 2023, pp. 33-35, doi: 10.1109/
ICASI57738.2023.10179494.
[4] C. Zhang et al., "Insulator Profile Detection of Transmission Line Based on Traditional Edge Detection Algorithm," 2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA), Dalian, China, 2020, pp. 267-269, doi: 10.1109/
ICAICA50127.2020.9181907.
[5] Z. Yang, "Research on Wildfire Smoke Detection Method Based on Improved YOLO11," 2025 5th International Conference on Consumer Electronics and Computer Engineering (ICCECE), Dongguan, China, 2025, pp. 516-519, doi: 10.1109/
ICCECE65250.2025.10985180.
[6] Y. Wang, F. Pan, Z. Li, X. Xin and W. Li, "CoT-YOLOv8: Improved YOLOv8 for Aerial images Small Target Detection," 2023 China
Automation Congress (CAC), Chongqing, China, 2023, pp. 4943-4948, doi: 10.1109/CAC59555.2023.10451989.
[7] Q. Song, Z. Liu and H. Jiang, "Coal gangue detection method based on improved YOLOv5," 2022 3rd International Conference
on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), Xian, China, 2022, pp. 466-469, doi: 10.1109/
ICBAIE56435.2022.9985920.
[8] D. Yang, X. Fan, X. Meng and D. Zhao, "Neural Image Compression with Multi-Scale Depthwise Separable Dilated Convolution and
Multi-Distribution Mixture Entropy Model," 2025 Data Compression Conference (DCC), Snowbird, UT, USA, 2025, pp. 411-411, doi:
10.1109/DCC62719.2025.00098.
[9] S. Du, B. Zhang, P. Zhang and P. Xiang, "An Improved Bounding Box Regression Loss Function Based on CIOU Loss for Multi-scale
Object Detection," 2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML), Chengdu, China,
2021, pp. 92-98, doi: 10.1109/PRML52754.2021.9520717.
[10] Y. Chen, X. Li, Z. He, H. Chen, J. Chen and B. Wu, "IoU_MDA: An Occluded Object Detection Algorithm Based on Fuzzy
Sample Anchor Box IoU Matching Degree Deviation Aware," in IEEE Access, vol. 12, pp. 47630-47645, 2024, doi: 10.1109/
ACCESS.2024.3375109.
[11] K. Li, D. Gao, Z. Yang and X. Wei, "SCAT: Shared-Convolution Adaptation Tuning for Foreground Segmentation," ICASSP 2025
- 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, pp. 1-5, doi:
10.1109/ICASSP49660.2025.10888732.
[12] A. Youssef, P. F. Driessen, F. Gebali, M. Belaid and S. Harrison, "Enhancement of time compression overlap-add using multirate downsample upsample shift add algorithm," 2017 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing
(PACRIM), Victoria, BC, Canada, 2017, pp. 1-5, doi: 10.1109/PACRIM.2017.8121904.
[13] J. Joung and C. Yuen, "Channel Shuffling for Double SpaceTime Line Coded Systems," in IEEE Transactions on Vehicular Technology, vol. 73, no. 2, pp. 2860-2865, Feb. 2024, doi: 10.1109/TVT.2023.3314455.
[14] B. Jin, Y. Peng, X. Kuang, Z. Zhang, Z. Lian and B. Wang, "Robust Dynamic Hand Gesture Recognition Based on Millimeter Wave Radar Using Atten-TsNN," in IEEE Sensors Journal, vol. 22, no. 11, pp. 10861-10869, 1 June1, 2022, doi: 10.1109/JSEN.2022.3170311.
[15] J. Si, S. L. Harris and E. Yfantis, "A Dynamic ReLU on Neural Network," 2018 IEEE 13th Dallas Circuits and Systems Conference
(DCAS), Dallas, TX, USA, 2018, pp. 1-6, doi: 10.1109/DCAS.2018.8620116.
[16] Y. Srivastava, V. Murali and S. R. Dubey, "PSNet: Parametric Sigmoid Norm Based CNN for Face Recognition," 2019 IEEE Conference on Information and Communication Technology, Allahabad, India, 2019, pp. 1-4, doi: 10.1109/CICT48419.2019.9066169.
DOI: http://dx.doi.org/10.70711/aitr.v2i11.7409
Refbacks
- There are currently no refbacks.
